{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:K4ROG2TQA6DJVE3GKSBAO25FPW","short_pith_number":"pith:K4ROG2TQ","schema_version":"1.0","canonical_sha256":"5722e36a7007869a93665482076ba57db13a14db3876b55fbe72afd0fe852d83","source":{"kind":"arxiv","id":"2508.18600","version":1},"attestation_state":"computed","paper":{"title":"Bias-Adjusted LLM Agents for Human-Like Decision-Making via Behavioral Economics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","econ.GN","q-fin.EC"],"primary_cat":"cs.GT","authors_text":"Ayato Kitadai, Nariaki Nishino, Yusuke Fukasawa","submitted_at":"2025-08-26T02:02:18Z","abstract_excerpt":"Large language models (LLMs) are increasingly used to simulate human decision-making, but their intrinsic biases often diverge from real human behavior--limiting their ability to reflect population-level diversity. We address this challenge with a persona-based approach that leverages individual-level behavioral data from behavioral economics to adjust model biases. Applying this method to the ultimatum game--a standard but difficult benchmark for LLMs--we observe improved alignment between simulated and empirical behavior, particularly on the responder side. While further refinement of trait "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2508.18600","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2025-08-26T02:02:18Z","cross_cats_sorted":["cs.MA","econ.GN","q-fin.EC"],"title_canon_sha256":"93de15a6bcd7f2e7a4ae0e21da901f6c3f812457502deafa2800c7c053a5bedf","abstract_canon_sha256":"59ebbe78a16d62b28cc514ca49f3aca005fa6496d9814a2cfe813cbb5803dd54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:27.507001Z","signature_b64":"X3OjagCwDPQFqdI+vaXFvMTfBc+4mPBlp60b8ZBk5iKI2zh7GyRxBOfc4AlcCtPSjlq8eTrPcMgYk/FWkDECAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5722e36a7007869a93665482076ba57db13a14db3876b55fbe72afd0fe852d83","last_reissued_at":"2026-07-05T11:59:27.506558Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:27.506558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bias-Adjusted LLM Agents for Human-Like Decision-Making via Behavioral Economics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","econ.GN","q-fin.EC"],"primary_cat":"cs.GT","authors_text":"Ayato Kitadai, Nariaki Nishino, Yusuke Fukasawa","submitted_at":"2025-08-26T02:02:18Z","abstract_excerpt":"Large language models (LLMs) are increasingly used to simulate human decision-making, but their intrinsic biases often diverge from real human behavior--limiting their ability to reflect population-level diversity. We address this challenge with a persona-based approach that leverages individual-level behavioral data from behavioral economics to adjust model biases. Applying this method to the ultimatum game--a standard but difficult benchmark for LLMs--we observe improved alignment between simulated and empirical behavior, particularly on the responder side. While further refinement of trait "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18600","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2508.18600/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2508.18600","created_at":"2026-07-05T11:59:27.506617+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.18600v1","created_at":"2026-07-05T11:59:27.506617+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18600","created_at":"2026-07-05T11:59:27.506617+00:00"},{"alias_kind":"pith_short_12","alias_value":"K4ROG2TQA6DJ","created_at":"2026-07-05T11:59:27.506617+00:00"},{"alias_kind":"pith_short_16","alias_value":"K4ROG2TQA6DJVE3G","created_at":"2026-07-05T11:59:27.506617+00:00"},{"alias_kind":"pith_short_8","alias_value":"K4ROG2TQ","created_at":"2026-07-05T11:59:27.506617+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13038","citing_title":"Nous: An Attempt to Extract and Inject the Cognition Behind Prediction-Market Behavior","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K4ROG2TQA6DJVE3GKSBAO25FPW","json":"https://pith.science/pith/K4ROG2TQA6DJVE3GKSBAO25FPW.json","graph_json":"https://pith.science/api/pith-number/K4ROG2TQA6DJVE3GKSBAO25FPW/graph.json","events_json":"https://pith.science/api/pith-number/K4ROG2TQA6DJVE3GKSBAO25FPW/events.json","paper":"https://pith.science/paper/K4ROG2TQ"},"agent_actions":{"view_html":"https://pith.science/pith/K4ROG2TQA6DJVE3GKSBAO25FPW","download_json":"https://pith.science/pith/K4ROG2TQA6DJVE3GKSBAO25FPW.json","view_paper":"https://pith.science/paper/K4ROG2TQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.18600&json=true","fetch_graph":"https://pith.science/api/pith-number/K4ROG2TQA6DJVE3GKSBAO25FPW/graph.json","fetch_events":"https://pith.science/api/pith-number/K4ROG2TQA6DJVE3GKSBAO25FPW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K4ROG2TQA6DJVE3GKSBAO25FPW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K4ROG2TQA6DJVE3GKSBAO25FPW/action/storage_attestation","attest_author":"https://pith.science/pith/K4ROG2TQA6DJVE3GKSBAO25FPW/action/author_attestation","sign_citation":"https://pith.science/pith/K4ROG2TQA6DJVE3GKSBAO25FPW/action/citation_signature","submit_replication":"https://pith.science/pith/K4ROG2TQA6DJVE3GKSBAO25FPW/action/replication_record"}},"created_at":"2026-07-05T11:59:27.506617+00:00","updated_at":"2026-07-05T11:59:27.506617+00:00"}